Deep-Learning-Based 3D Reconstruction: A Review and Applications
In recent years, deep learning models have been widely used in 3D reconstruction fields and have made remarkable progress. How to stimulate deep academic interest to effectively manage the explosive augmentation of 3D models has been a research hotspot. This work shows mainstream 3D model retrieval...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2022-01-01
|
Series: | Applied Bionics and Biomechanics |
Online Access: | http://dx.doi.org/10.1155/2022/3458717 |
_version_ | 1798001742465466368 |
---|---|
author | Yinhai Li Fei Wang Xinhua Hu |
author_facet | Yinhai Li Fei Wang Xinhua Hu |
author_sort | Yinhai Li |
collection | DOAJ |
description | In recent years, deep learning models have been widely used in 3D reconstruction fields and have made remarkable progress. How to stimulate deep academic interest to effectively manage the explosive augmentation of 3D models has been a research hotspot. This work shows mainstream 3D model retrieval algorithm programs based on deep learning currently developed remotely, and further subdivides their advantages and disadvantages according to the behavior evaluation of the algorithm programs obtained by trial. According to other restoration applications, the main 3D model retrieval algorithms can be divided into two categories: (1) 3D standard restoration methods supported by the model, i.e., both the restored object and the recalled object are 3D models. It can be further divided into voxel-based, point coloring-based, and appearance-based methods, and (2) cross-domain 3D model recovery methods supported by 2D replicas, that is, the retrieval motivation is 2D images, and the recovery appearance is 3D models, including retrieval methods supported by 2D display, 2D depiction-based realistic replication and 3D mold recovery methods. Finally, the work proposed novel 3D fashion retrieval algorithms supported by deep science that are analyzed and ventilated, and the unaccustomed directions of future development are prospected. |
first_indexed | 2024-04-11T11:40:59Z |
format | Article |
id | doaj.art-3992be1ba0d04d43b8e84b1e9bafb938 |
institution | Directory Open Access Journal |
issn | 1754-2103 |
language | English |
last_indexed | 2024-04-11T11:40:59Z |
publishDate | 2022-01-01 |
publisher | Hindawi Limited |
record_format | Article |
series | Applied Bionics and Biomechanics |
spelling | doaj.art-3992be1ba0d04d43b8e84b1e9bafb9382022-12-22T04:25:48ZengHindawi LimitedApplied Bionics and Biomechanics1754-21032022-01-01202210.1155/2022/3458717Deep-Learning-Based 3D Reconstruction: A Review and ApplicationsYinhai Li0Fei Wang1Xinhua Hu2College of Mechanical and Electrical EngineeringCollege of Creative ArtsCollege of Mechanical and Electrical EngineeringIn recent years, deep learning models have been widely used in 3D reconstruction fields and have made remarkable progress. How to stimulate deep academic interest to effectively manage the explosive augmentation of 3D models has been a research hotspot. This work shows mainstream 3D model retrieval algorithm programs based on deep learning currently developed remotely, and further subdivides their advantages and disadvantages according to the behavior evaluation of the algorithm programs obtained by trial. According to other restoration applications, the main 3D model retrieval algorithms can be divided into two categories: (1) 3D standard restoration methods supported by the model, i.e., both the restored object and the recalled object are 3D models. It can be further divided into voxel-based, point coloring-based, and appearance-based methods, and (2) cross-domain 3D model recovery methods supported by 2D replicas, that is, the retrieval motivation is 2D images, and the recovery appearance is 3D models, including retrieval methods supported by 2D display, 2D depiction-based realistic replication and 3D mold recovery methods. Finally, the work proposed novel 3D fashion retrieval algorithms supported by deep science that are analyzed and ventilated, and the unaccustomed directions of future development are prospected.http://dx.doi.org/10.1155/2022/3458717 |
spellingShingle | Yinhai Li Fei Wang Xinhua Hu Deep-Learning-Based 3D Reconstruction: A Review and Applications Applied Bionics and Biomechanics |
title | Deep-Learning-Based 3D Reconstruction: A Review and Applications |
title_full | Deep-Learning-Based 3D Reconstruction: A Review and Applications |
title_fullStr | Deep-Learning-Based 3D Reconstruction: A Review and Applications |
title_full_unstemmed | Deep-Learning-Based 3D Reconstruction: A Review and Applications |
title_short | Deep-Learning-Based 3D Reconstruction: A Review and Applications |
title_sort | deep learning based 3d reconstruction a review and applications |
url | http://dx.doi.org/10.1155/2022/3458717 |
work_keys_str_mv | AT yinhaili deeplearningbased3dreconstructionareviewandapplications AT feiwang deeplearningbased3dreconstructionareviewandapplications AT xinhuahu deeplearningbased3dreconstructionareviewandapplications |